Abstract
The interpolation of correspondences (EpicFlow) was widely used for optical flflow estimation in most-recent works. It has the advantage of edge-preserving and effifi- ciency. However, it is vulnerable to input matching noise, which is inevitable in modern matching techniques. In this paper, we present a Robust Interpolation method of Correspondences (called RicFlow) to overcome the weakness. First, the scene is over-segmented into superpixels to revitalize an early idea of piecewise flflow model. Then, each model is estimated robustly from its support neighbors based on a graph constructed on superpixels. We propose a propagation mechanism among the pieces in the estimation of models. The propagation of models is signifificantly more effificient than the independent estimation of each model, yet retains the accuracy. Extensive experiments on three public datasets demonstrate that RicFlow is more robust than EpicFlow, and it outperforms state-of-the-art methods